让AI程序在出错时能自动修复，只多花一次调用就大幅提升成功率。
REPOT: Recoverable Program-of-Thought via Checkpoint Repair
- 出错后通过检查点信息定位失败点，仅需一次LLM调用恢复执行
- 在多个模型上提升3%到11%成功率，最高达96.9%
- 适合需要高可靠性的自动化任务与复杂推理场景
一次性思维链（PoT）生成一个打印基础动作计划的Python程序；一旦出现无效动作，整个轨迹即失效。我们提出可恢复的思维链（RePoT）：一种确定性验证重播机制，将计划逐步推进至首个无效转移点，随后仅需一次LLM调用即可从已验证前缀处恢复。RePoT在约14%的失败问题上最多增加一次调用成本。在四个封闭模型配置下，RePoT相较PoT提升3%至11%，在gpt-5.4-mini-medium上达到96.9%对比86.3%。相较于同预算的PoT重试基线，RePoT在Gemini上胜出+3.8pp（95%置信区间[+2.2,+5.4]），在GPT-medium和Claude上无显著差异，在GPT-mini上稍逊——这一能力扩展模式启发我们提出自适应RePoT，基于已验证前缀长度的规则调度器，动态选择补全或重试。该方法在PlanBench Blocksworld上提升1.1%至11.4%，对四种开放权重模型提升3.3%至20.0%（其中三款提升显著）。在Derail-550可控恢复基准测试中，所有具备检查点信息的条件均实现≥30%（GPT-medium）和≥70%（Gemini）的提升，而仅依赖错误反馈的方案最高仅3.1%，表明检查点信息才是关键恢复信号，而非具体前缀尾部内容。
原文摘要 · Abstract (English)
One-shot Program-of-Thought (PoT) emits a Python program that prints a primitive-action plan; a single invalid action silently invalidates the trajectory. We introduce RePoT (Recoverable PoT): a deterministic verified replay that walks the plan through the environment to its first invalid transition, then one LLM call that resumes from the verified prefix. RePoT costs at most one extra LLM call on the ~14% of problems where PoT fails. RePoT beats PoT by +3 to +11pp across four closed-model configurations on PuzzleZoo-775 and peaks at 96.9% vs 86.3% on gpt-5.4-mini-medium; against the matched-budget PoT-retry baseline, RePoT wins decisively on Gemini (+3.8pp, 95% CI [+2.2,+5.4]), is within sampling noise on GPT-medium and Claude, and loses on GPT-mini -- a capability-scaling pattern we begin to address with Adaptive RePoT, a rule-based dispatcher that routes between suffix repair and a fresh PoT retry based on verified-prefix length (preliminary). We replicate on PlanBench Blocksworld (+1.1 to +11.4pp) and on four open-weights models (+3.3 to +20.0pp on three of four). On Derail-550, our controlled recovery benchmark, every condition with access to checkpoint information clears >=30% on GPT-medium and >=70% on Gemini, vs <=3.1% for error-only feedback -- showing that checkpoint information, not the specific verified-prefix tail, is the load-bearing recovery signal.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。